© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 201664
    Prev
    Next
    INDEX
    Explanations

    live set

    np_acts-logits-general · gemini-2.5-flash-lite

    operating system searches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     रहेंगी
    0.52
     Dienstag
    0.49
     lymphatiques
    0.48
    莳
    0.47
     வயி
    0.47
     смотрите
    0.46
    imir
    0.46
    ッズ
    0.46
    枢
    0.46
    尼亚克
    0.46
    POSITIVE LOGITS
     entries
    0.49
     wading
    0.49
     stalking
    0.49
     dispos
    0.45
     diversifying
    0.45
    ]}{
    0.45
     turismo
    0.44
     quotas
    0.43
    ছে
    0.43
     grinding
    0.43
    Activations Density 0.001%

    No Known Activations